paper-with-me

Papers

UTSD: Unified Time Series Diffusion Model

2024-12-04 · Xiangkai Ma, Xiaobin Hong, Wenzhong Li, Sanglu Lu

Transformer-based architectures have achieved unprecedented success in time series analysis. However, facing the challenge of across-domain modeling, existing studies utilize statistical prior as prompt engineering fails under the huge distribution shift among various domains. In this paper, a Unified Time Series Diffusion (UTSD) model is established for the first time to model the multi-domain probability distribution, utilizing the powerful probability distribution modeling ability of Diffusion. Unlike the autoregressive models that capture the conditional probabilities of the prediction horizon to the historical sequence, we use a diffusion denoising process to model the mixture distribution of the cross-domain data and generate the prediction sequence for the target domain directly utilizing conditional sampling. The proposed UTSD contains three pivotal designs: (1) The condition network captures the multi-scale fluctuation patterns from the observation sequence, which are utilized as context representations to guide the denoising network to generate the prediction sequence; (2) Adapter-based fine-tuning strategy, the multi-domain universal representation learned in the pretraining stage is utilized for downstream tasks in target domains; (3) The diffusion and denoising process on the actual sequence space, combined with the improved classifier free guidance as the conditional generation strategy, greatly improves the stability and accuracy of the downstream task. We conduct extensive experiments on mainstream benchmarks, and the pre-trained UTSD outperforms existing foundation models on all data domains, exhibiting superior zero-shot generalization ability. After training from scratch, UTSD achieves comparable performance against domain-specific proprietary models. The empirical results validate the potential of UTSD as a time series foundational model.

📄 PDF Abstract BibTeX arXiv:2412.03068

Code (0)

등록된 구현이 없습니다.

Tasks

DenoisingmodelPrompt EngineeringTime SeriesTime Series AnalysisZero-shot Generalization

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

UniDiff: A Unified Diffusion Framework for Multimodal Time Series Forecasting

2025-12-08 · Da Zhang, Bingyu Li, Zhuyuan Zhao, Junyu Gao 외 arxiv

As multimodal data proliferates across diverse real-world applications, leveraging heterogeneous information such as texts and timestamps for accurate time series forecasting (TSF) has become a critical challenge. While …

Time Series Forecasting

SBBTS: A Unified Schrödinger-Bass Framework for Synthetic Financial Time Series

2026-04-08 · Alexandre Alouadi, Grégoire Loeper, Célian Marsala, Othmane Mazhar 외 arxiv

We study the problem of generating synthetic time series that reproduce both marginal distributions and temporal dynamics, a central challenge in financial machine learning. Existing approaches typically fail to jointly …

Data Augmentation

Unified Discrete Diffusion for Categorical Data

2024-02-06 · Lingxiao Zhao, Xueying Ding, Lijun Yu, Leman Akoglu

Discrete diffusion models have seen a surge of attention with applications on naturally discrete data such as language and graphs. Although discrete-time discrete diffusion has been established for a while, only recently…

Denoising

EventTSF: Event-Aware Non-Stationary Time Series Forecasting

2025-08-19 · Yunfeng Ge, Ming Jin, Yiji Zhao, Hongyan Li 외 arxiv

Time series forecasting is vital in diverse sectors such as energy and transportation, where non-stationary dynamics are deeply intertwined with external events in other modalities such as texts. However, incorporating n…

Time Series Forecasting

Towards a Unified Generative Model for Scarce Time Series with Domain Experts

2026-06-13 · Zihao Yao, Qi Zheng, Jiankai Zuo, Yaying Zhang arxiv

Synthesizing realistic time series with generative models has wide-ranging applications in real-world scenarios. Despite recent progress, most existing methods are trained under the assumption of abundant training data, …